The following addresses PR109046 by adding an optimization to forwprop
to combine a piecewise complex load to a complex load when there are
no uses of the components. That's something useful in general and
easier to do than avoiding the splitting in complex lowering.
The testcase exercises both the manual and the complex lowering case.
Bootstrapped and tested on x86_64-unknown-linux-gnu, OK?
Thanks,
Richard.
PR tree-optimization/109046
* tree-ssa-forwprop.cc (pass_forwprop::execute): Combine
piecewise complex loads.
* gcc.dg/tree-ssa/forwprop-39.c: New testcase.
---
gcc/testsuite/gcc.dg/tree-ssa/forwprop-39.c | 15 ++++++++++
gcc/tree-ssa-forwprop.cc | 31 ++++++++++++++++++++-
2 files changed, 45 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/forwprop-39.c
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/forwprop-39.c
b/gcc/testsuite/gcc.dg/tree-ssa/forwprop-39.c
new file mode 100644
index 00000000000..eb2930e77fd
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/forwprop-39.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-std=c11 -O2 -fdump-tree-forwprop1 -fdump-tree-optimized" } */
+
+#include <complex.h>
+
+extern void push1(void *p, float _Complex x);
+void foo (void *q, float _Complex *x)
+{
+ float r = __real *x;
+ float i = __imag *x;
+ push1 (q, CMPLXF (r, i));
+}
+
+/* { dg-final { scan-tree-dump-not "COMPLEX_EXPR" "forwprop1" } } */
+/* { dg-final { scan-tree-dump-not "REALPART_EXPR" "optimized" } } */
diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc
index 03fe0a3f6df..3111a2b96a3 100644
--- a/gcc/tree-ssa-forwprop.cc
+++ b/gcc/tree-ssa-forwprop.cc
@@ -3669,7 +3669,8 @@ pass_forwprop::execute (function *fun)
/* Rewrite stores of a single-use complex build expression
to component-wise stores. */
use_operand_p use_p;
- gimple *use_stmt;
+ gimple *use_stmt, *def1, *def2;
+ tree rhs2;
if (single_imm_use (lhs, &use_p, &use_stmt)
&& gimple_store_p (use_stmt)
&& !gimple_has_volatile_ops (use_stmt)
@@ -3703,6 +3704,34 @@ pass_forwprop::execute (function *fun)
release_defs (stmt);
gsi_remove (&gsi, true);
}
+ /* Rewrite a component-wise load of a complex to a complex
+ load if the components are not used separately. */
+ else if (TREE_CODE (rhs) == SSA_NAME
+ && has_single_use (rhs)
+ && ((rhs2 = gimple_assign_rhs2 (stmt)), true)
+ && TREE_CODE (rhs2) == SSA_NAME
+ && has_single_use (rhs2)
+ && (def1 = SSA_NAME_DEF_STMT (rhs),
+ gimple_assign_load_p (def1))
+ && (def2 = SSA_NAME_DEF_STMT (rhs2),
+ gimple_assign_load_p (def2))
+ && (gimple_vuse (def1) == gimple_vuse (def2))
+ && gimple_assign_rhs_code (def1) == REALPART_EXPR
+ && gimple_assign_rhs_code (def2) == IMAGPART_EXPR
+ && operand_equal_p (TREE_OPERAND (gimple_assign_rhs1
+ (def1), 0),
+ TREE_OPERAND (gimple_assign_rhs1
+ (def2), 0)))
+ {
+ tree cl = TREE_OPERAND (gimple_assign_rhs1 (def1), 0);
+ gimple_assign_set_rhs_from_tree (&gsi, unshare_expr (cl));
+ gcc_assert (gsi_stmt (gsi) == stmt);
+ gimple_set_vuse (stmt, gimple_vuse (def1));
+ gimple_set_modified (stmt, true);
+ gimple_stmt_iterator gsi2 = gsi_for_stmt (def1);
+ gsi_remove (&gsi, false);
+ gsi_insert_after (&gsi2, stmt, GSI_SAME_STMT);
+ }
else
gsi_next (&gsi);
}
--
2.35.3
